Assessing heterogeneity in treatment initiation guidelines in longitudinal randomized controlled trials

被引:0
作者
Cho, Hyunkeun Ryan [1 ]
Kim, Seonjin [2 ]
机构
[1] Univ Iowa, Dept Biostat, 145 N Riverside Dr, Iowa City, IA 52242 USA
[2] Miami Univ, Dept Stat, 105 Tallawanda Rd, Oxford, OH 45056 USA
关键词
Causal inference; Heterogeneous guideline effects; Longitudinal data; Quadratic inference function; Weighted score functions; MARGINAL STRUCTURAL MODELS; ANTIRETROVIRAL THERAPY; PROPENSITY SCORE; CAUSAL INFERENCE; SELECTION; DURATION;
D O I
10.1016/j.jspi.2024.106226
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Treatment initiation guidelines are essential in healthcare, dictating when patients begin therapy. These guidelines are typically assessed through randomized controlled trials (RCTs) to measure their average effect on a population. However, this method may not fully account for patient heterogeneity. We introduce a refined analysis methodology that accounts for diverse times to treatment initiation (TTI) arising from these guidelines. We offer a more detailed perspective on the guidelines' impact by analyzing homogeneous subpopulations based on their TTI. We develop a longitudinal regression model with smooth time functions to capture dynamic changes in average guideline effects on subpopulations (AGES). A unique weighting mechanism creates pseudo-subpopulations from RCT data, enabling consistent and precise estimation of smooth functions. The efficacy of our approach is validated through theoretical and numerical studies, underscoring its capacity to provide insightful statistical inferences. We exemplify the utility of our methodology by applying it to an RCT of the World Health Organization (WHO) guideline for adults with HIV. This analysis promises to enhance the evaluation of treatment initiation guidelines, leading to more personalized and efficient patient care.
引用
收藏
页数:12
相关论文
共 33 条
[1]   Estimating the labor market impact of voluntary military service using social security data on military applicants [J].
Angrist, JD .
ECONOMETRICA, 1998, 66 (02) :249-288
[2]   Efficient estimation for longitudinal data by combining large-dimensional moment conditions [J].
Cho, Hyunkeun ;
Qu, Annie .
ELECTRONIC JOURNAL OF STATISTICS, 2015, 9 (01) :1315-1334
[3]   Adjusting a subject-specific time of event in longitudinal studies [J].
Cho, Hyunkeun Ryan ;
Kim, Seonjin ;
Lee, Myung Hee .
STATISTICAL METHODS IN MEDICAL RESEARCH, 2020, 29 (07) :1787-1798
[4]   CD4 deficit and tuberculosis risk persist with delayed antiretroviral therapy: 5-year data from CIPRA HT-001 [J].
Collins, S. E. ;
Juste, M. A. Jean ;
Koenig, S. P. ;
Secours, R. ;
Ocheretina, O. ;
Bernard, D. ;
Riviere, C. ;
Calnan, M. ;
Dunning, A. ;
Rua, S. M. Hurtado ;
Johnson, W. D., Jr. ;
Pape, J. W. ;
Fitzgerald, D. W. ;
Severe, P. .
INTERNATIONAL JOURNAL OF TUBERCULOSIS AND LUNG DISEASE, 2015, 19 (01) :50-57
[5]   Estimation of conditional densities and sensitivity measures in nonlinear dynamical systems [J].
Fan, JQ ;
Yao, QW ;
Tong, H .
BIOMETRIKA, 1996, 83 (01) :189-206
[6]   A crossvalidation method for estimating conditional densities [J].
Fan, JQ ;
Yim, TH .
BIOMETRIKA, 2004, 91 (04) :819-834
[7]  
Field MJ., 1990, Clinical practice guidelines: directions for a new program
[8]   On the role of the propensity score in efficient semiparametric estimation of average treatment effects [J].
Hahn, JY .
ECONOMETRICA, 1998, 66 (02) :315-331
[9]   Characterizing selection bias using experimental data [J].
Heckman, J ;
Ichimura, H ;
Smith, J ;
Todd, P .
ECONOMETRICA, 1998, 66 (05) :1017-1098
[10]  
Heckman J., 1985, LONGITUDINAL ANAL LA, P156, DOI DOI 10.1017/CCOL0521304539.004